Consensus scoring model for the molecular docking study of mTOR kinase inhibitor

摘要

Graphical abstractA series of 25 kinds of mTOR inhibitors with antitumor activity has been selected for the molecular docking study of mTOR kinase inhibitor. Two best calculated models10and22with same BEI indice: for model10, training set R2=0.767, Q2=0.647, RMSE=0.024, and for test set R2=0.932, RMSE=0.026; for model22, raining set R2=0.790, Q2=0.627, RMSE=0.023, and for test set R2=0.955, RMSE=0.020.Display OmittedHighlights?The predicted poses of these ligands revaluated by twenty-six available scoring functions.?Three ligand efficiency indices instead of pIC50as the activity could be used in this study.?Consensus scoring models are trained based on the obtained rescoring results by the partial least squares (PLS) method.